Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

Rakesh, M and Kundu, JN and Jampani, V and Babu, RV (2021) Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery. In: 35th Conference on Neural Information Processing Systems, NeurIPS 2021, 6 - 14 December 2021, Virtual, Online, pp. 4582-4593.

PDF NeurIPS 2021_6_4582-4593_2021 .pdf - Published Version Restricted to Registered users only Download (6MB) | Request a copy

Abstract

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at deployment is highly inconvenient. However, we realize that standard foreground silhouette estimation techniques (on static camera feeds) remain unaffected by domain-shifts. Motivated by this, we propose a novel target adaptation framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. However, in the absence of any auxiliary cue (multi-view, depth, or 2D pose), an isolated silhouette loss fails to provide a reliable pose-specific gradient and requires to be employed in tandem with a topology-centric loss. To this end, we develop a series of convolution-friendly spatial transformations in order to disentangle a topological-skeleton representation from the raw silhouette. Such a design paves the way to devise a Chamfer-inspired spatial topological-alignment loss via distance field computation, while effectively avoiding any gradient hindering spatial-to-pointset mapping. Experimental results demonstrate our superiority against prior-arts in self-adapting a source trained model to diverse unlabeled target domains, such as a) in-the-wild datasets, b) low-resolution image domains, and c) adversarially perturbed image domains (via UAP).

Item Type:	Conference Paper
Publication:	Advances in Neural Information Processing Systems
Publisher:	Neural information processing systems foundation
Additional Information:	The copyright for this article belongs to the Neural information processing systems foundation.
Keywords:	3D human pose estimation; Adaptation framework; Estimation techniques; Human pose; Image domain; Model-based OPC; Pose recovery; Static cameras; Synthetic sources; Target domain
Department/Centre:	Division of Electrical Sciences > Electrical Engineering Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	27 Jun 2022 07:31
Last Modified:	27 Jun 2022 07:31
URI:	https://eprints.iisc.ac.in/id/eprint/73997

Actions (login required)

View Item